DeepSeek-R1

Used large-scale reinforcement learning to shape reasoning and released both full and distilled model weights.

CurrentReasoningCodingOpen weights

MODEL NUMBER018

Specifications

Only published specifications are shown.

Total parameters

671B

Active parameters

37B

Architecture

MoE

Context

128K

Input modalities

Text

Open weights

Yes

License

MIT

Status

Current

Used large-scale reinforcement learning to shape reasoning and released both full and distilled model weights.

R1 brought open-weight reasoning models into mainstream global comparison and accelerated replication of RL-based reasoning recipes.

PreviousDeepSeek-V3671B · 128K ctx

CurrentDeepSeek-R1671B · 128K ctx

New capabilities Reasoning Chain of thought

MLA

ReasoningCodingChain of thought

2025-01-20Open weights

DeepSeek-R1 and its distilled models were released with open weights.

Select a card to view the related model.